R Notebook

library(rvest)
library(dplyr)
library(tidyverse)
library(plotly)

Function to get NBA roster for a specified year

get_nba_roster <- function(year) {
  # Construct the URL for the specified year
  url <- paste0("https://www.basketball-reference.com/leagues/NBA_", year, "_per_game.html")
  
  # Read the HTML content from the URL
  webpage <- read_html(url)


  # Extract the table containing the player statistics
  roster_table <- webpage %>%
    html_node("table#per_game_stats") %>%
    html_table(fill = TRUE)
  
  roster_table <- roster_table[-which(roster_table$Player=='League Average'),]
  # Clean the data (remove header rows that might be duplicated)
  roster_table <- roster_table %>%
    filter(Player != "Player")
    return(roster_table)
}

# Function to get NBA advanced stats for a specified year
get_nba_advanced_stats <- function(year) {
  # Construct the URL for the specified year
  url <- paste0("https://www.basketball-reference.com/leagues/NBA_", year, "_advanced.html")
  
  # Read the HTML content from the URL
  webpage <- read_html(url)
  
  # Extract the table containing the advanced player statistics
  advanced_stats_table <- webpage %>%
    html_node("table#advanced_stats") %>%
    html_table(fill = TRUE)
  
  # Clean the data (remove header rows that might be duplicated)
 # advanced_stats_table <- advanced_stats_table %>%
  #  filter(Player != "Player")
  
  return(advanced_stats_table)
}

# Example usage
year <- 2018  # Specify the year
nba_advanced_stats <- get_nba_advanced_stats(year)

# Print the first few rows of the advanced stats
head(nba_advanced_stats)

NA
NA

combined_nba_stats<-function(year){
get_nba_roster2 <- function(year) {
  # Construct the URL for the specified year
  url <- paste0("https://www.basketball-reference.com/leagues/NBA_", year, "_per_game.html")
  
  # Read the HTML content from the URL
  webpage <- read_html(url)


  # Extract the table containing the player statistics
  roster_table <- webpage %>%
    html_node("table#per_game_stats") %>%
    html_table(fill = TRUE)
  
  # Clean the data (remove header rows that might be duplicated)
  roster_table <- roster_table %>%
    filter(Player != "Player")
    return(roster_table)
}
  
  year <- 2023  # Specify the year
nba_roster2 <- get_nba_roster2(year)

#Print the first few rows of the roster
head(nba_roster)
tail(nba_roster)


#take out the N/A 
nba_roster2<-na.omit(nba_roster2)


# Convert specific columns from character to double

nba_roster2 %>%
   mutate(across(G:PTS, as.numeric))

#ADVANCED STATS

# Function to get NBA advanced stats for a specified year
get_nba_advanced_stats <- function(year) {
  # Construct the URL for the specified year
  url <- paste0("https://www.basketball-reference.com/leagues/NBA_", year, "_advanced.html")
  
  # Read the HTML content from the URL
  webpage <- read_html(url)
  
  # Extract the table containing the advanced player statistics
  advanced_stats_table <- webpage %>%
    html_node("table#advanced_stats") %>%
    html_table(fill = TRUE)
  
  # Clean the data (remove header rows that might be duplicated)
 # advanced_stats_table <- advanced_stats_table %>%
  #  filter(Player != "Player")
  
  return(advanced_stats_table)
}

# Example usage
year <- 2023  # Specify the year
nba_advanced_stats2<- get_nba_advanced_stats(year)

# Print the first few rows of the advanced stats
head(nba_advanced_stats2)



#want to order by alphabetic name to make cleaning out the filler headers from the dataset
AO_nba_advanced_stats2<- nba_advanced_stats2[order(nba_advanced_stats2$Player),]





#remove na from dataframe
AO_nba_advanced_stats2 %>% 
  select(where(~!all(is.na(.))))
#removing column 20 and 25 from dataframe since theyre blanks
AO_nba_advanced_stats2<-AO_nba_advanced_stats2[,-20]
AO_nba_advanced_stats2<-AO_nba_advanced_stats2[,-24]


# remove filler rows that had been previously used as headers on webpage


AO_nba_advanced_stats2 <- AO_nba_advanced_stats2[AO_nba_advanced_stats2$Player != "Player",]

AO_nba_advanced_stats2$Player <- factor(AO_nba_advanced_stats2$Player)




#change range of cloumns <dbl> from <chr>

AO_nba_advanced_stats2 %>%
   mutate(across(G:VORP, as.numeric))
   
   nba_merge<-merge(nba_roster2, AO_nba_advanced_stats2, by.x = c("Rk", "Player", "Pos","Age", "Tm","G"), by.y = c("Rk", "Player", "Pos","Age", "Tm","G") , all.x = TRUE, all.y = TRUE)
   
}

Example usage

year <- 2018  # Specify the year
nba_roster <- combined_nba_stats(year)

Error in fix.by(by.x, x) : 'by' must specify a uniquely valid column

year <- 1980  # Specify the year
nba_roster <- get_nba_roster(year)

#Print the first few rows of the roster
head(nba_roster)

tail(nba_roster)

NA

nba_roster1<-nba_roster
nba_roster1$SGS<-nba_roster1$PTS+nba_roster1$TRB+nba_roster1$AST
nba_roster1$SGSind<-nba_roster1$SGS>24.3
head(nba_roster1)

NA

mean(nba_roster1$SGS>24.3,na.rm=T)

[1] 0.2016807

#Summary statistics

position_roster<-filter(nba_roster,Pos!="PG" )
position_roster

# Assuming 'nba_roster' is your data frame
input <- nba_roster1[, c('MP', 'PTS', 'Player','Pos','SGS','SGSind')]
input <- na.omit(input)
# Create the plotly scatter plot
fig <- plot_ly(input, x = ~MP, y = ~PTS, type = 'scatter', mode = 'markers',
               text = ~Player,  # This adds player names on hover
               hoverinfo = c('text',~MP), # Ensures that player names and data appear on hover
               color = ~SGSind,
               colors = c('green','red'),  # Colors points based on position
               marker = list(size = 10))

# Set the plot title and axis labels
fig <- fig %>% layout(title = "Minutes Played vs Points Scored",
                      xaxis = list(title = "Minutes Played", range = c(0, 48)),
                      yaxis = list(title = "Points", range = c(0, 35)))

fit<-lm(PTS~poly(MP,2),data=input)

# Add the best fit line to the plot
fig <- fig %>% add_lines(x = ~MP, 
                         y = fitted(fit), 
                         line = list(color = 'black'),
                         name = 'Best Fit Line')

# Show the plot
fig

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

saveWidget(fig, "MinPlayed_vs_PointScored.html")

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

#Data Visualization for Field Goals Attempled vs Field Goals Made

# Get the input values.
input_2 <- nba_roster1[, c('Player', 'MP', 'FGA', 'FG', 'SGS', 'SGSind')]

#input_2 <- na.omit(input_2)
# Set limits based on the data
b_FG <- max(input_2$FG, na.rm = TRUE)
b_FGA <- max(input_2$FGA, na.rm = TRUE)

# Create the plotly scatter plot
fig <- plot_ly(data = input_2, 
               x = ~FGA, 
               y = ~FG, 
               type = 'scatter', 
               mode = 'markers',
               marker = list(size = 10),
               text=~Player,
               hoverinfo = c('text',~MP), # Ensures that player names and data appear on hover
               color = ~SGSind,
               colors = c('green','red'))

# Customize the layout
fig <- fig %>% layout(title = 'Field Goal Attempts vs Field Goals Made',
                      xaxis = list(title = 'Field Goal Attempts', range = c(0.0, b_FGA)),
                      yaxis = list(title = 'Field Goals Made', range = c(0.0, b_FG)))

fit<-lm(FG~FGA,data=input_2)

# Add the best fit line to the plot
fig <- fig %>% add_lines(x = ~FGA, 
                         y = fitted(fit), 
                         line = list(color = 'black'),
                         name = 'Best Fit Line')

# Display the plot
fig

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

saveWidget(fig, "FGA_vs_FGMade.html")

A marker object has been specified, but markers is not in the mode
Adding markers to the mode...
A marker object has been specified, but markers is not in the mode
Adding markers to the mode...

# Assuming 'nba_roster' is your data frame
input <- nba_roster1[, c('MP', 'PTS', 'Player','Pos','SGS','SGSind')]
#input <- na.omit(input)

input_3 <- na.omit(input)
# Set limits based on the data
b_SGS <- max(input_2$SGS, na.rm = TRUE)+5

# Create the plotly scatter plot
fig <- plot_ly(input, x = ~MP, y = ~SGS, type = 'scatter', mode = 'markers',
               text = ~Player,  # This adds player names on hover
               hoverinfo = c('text',~SGS), # Ensures that player names and data appear on hover
               color = ~SGSind,
               colors = c('green','red'),  # Colors points based on position
               marker = list(size = 10))

# Set the plot title and axis labels
fig <- fig %>% layout(title = "Minutes Played vs Simple Game Score",
                      xaxis = list(title = "Minutes Played", range = c(0, 48)),
                      yaxis = list(title = "Simple Game Score", range = c(0, b_SGS)))

#fit<-lm(SGS~poly(MP,2),data=input)

# Add the best fit line to the plot
#fig <- fig %>% add_lines(x = ~MP, 
 #                        y = fitted(fit), 
  #                       line = list(color = 'black'),
   #                      name = 'Best Fit Line')

# Show the plot
fig

Warning: Ignoring 1 observations
Warning: Ignoring 1 observations

#saveWidget(fig, "MinPlayed_vs_SimpleGameScore.html")

summary(lm(FG~FGA,data=nba_roster1))

Call:
lm(formula = FG ~ FGA, data = nba_roster1)

Residuals:
    Min      1Q  Median      3Q     Max 
-1.5034 -0.2733 -0.0427  0.2415  1.8839 

Coefficients:
             Estimate Std. Error t value Pr(>|t|)    
(Intercept) -0.056479   0.030837  -1.832   0.0675 .  
FGA          0.458524   0.003893 117.773   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4483 on 662 degrees of freedom
  (1 observation deleted due to missingness)
Multiple R-squared:  0.9544,    Adjusted R-squared:  0.9544 
F-statistic: 1.387e+04 on 1 and 662 DF,  p-value: < 2.2e-16

nba_roster1E<-nba_roster1[which(nba_roster1$SGSind==T),]
summary(lm(FG~FGA,data=nba_roster1E))

Call:
lm(formula = FG ~ FGA, data = nba_roster1E)

Residuals:
    Min      1Q  Median      3Q     Max 
-0.9539 -0.4270 -0.1272  0.3286  1.6776 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  1.28971    0.36287   3.554 0.000719 ***
FGA          0.39030    0.02355  16.571  < 2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.5992 on 64 degrees of freedom
Multiple R-squared:  0.811, Adjusted R-squared:  0.808 
F-statistic: 274.6 on 1 and 64 DF,  p-value: < 2.2e-16

nba_roster1NE<-nba_roster1[which(nba_roster1$SGSind==F),]
summary(lm(FG~FGA,data=nba_roster1NE))

Call:
lm(formula = FG ~ FGA, data = nba_roster1NE)

Residuals:
     Min       1Q   Median       3Q      Max 
-1.41308 -0.24614 -0.03911  0.24207  1.76220 

Coefficients:
            Estimate Std. Error t value Pr(>|t|)    
(Intercept)  0.02751    0.03112   0.884    0.377    
FGA          0.43727    0.00472  92.639   <2e-16 ***
---
Signif. codes:  0 ‘***’ 0.001 ‘**’ 0.01 ‘*’ 0.05 ‘.’ 0.1 ‘ ’ 1

Residual standard error: 0.4022 on 596 degrees of freedom
Multiple R-squared:  0.9351,    Adjusted R-squared:  0.935 
F-statistic:  8582 on 1 and 596 DF,  p-value: < 2.2e-16

gg <- ggplot(data = nba_roster1 ) +  
 geom_density(aes(x=FG)) + geom_density(aes(x=FG, color=SGSind)) + geom_rug(aes(x=FG, color=SGSind)) + 
  ylab("") + 
  xlab("")

ggplotly(gg)%>% 
  layout(plot_bgcolor='#e5ecf6',   
             xaxis = list(   
               title='Time', 
               zerolinecolor = '#ffff',   
               zerolinewidth = 2,   
               gridcolor = 'ffff'),   
             yaxis = list(   
               title='Value A', 
               zerolinecolor = '#ffff',   
               zerolinewidth = 2,   
               gridcolor = 'ffff'),
         title = 'Curve and Rug Plot') 

Warning: Removed 1 row containing non-finite outside the scale range (`stat_density()`).
Warning: Removed 1 row containing non-finite outside the scale range (`stat_density()`).